文献速递神经MR

利用挖掘的标注对脑部MRI肿瘤检测模型进行半监督训练

Semisupervised Training of a Brain MRI Tumor Detection Model Using Mined Annotations.
PubMed 文献 · Radiology · 2022-01-18

本研究从癌症中心PACS中挖掘2012年1月至2017年12月的脑部MRI轴位T1增强图像及其线标注,转换为边界框后训练RetinaNet和Mask R-CNN肿瘤检测模型,并用最佳模型对训练图像自标注以扩充数据集。自标注后RetinaNet和Mask R-CNN的F1分数分别从0.886和0.908提升至0.935和0.954(P < .001),表明半监督学习能显著改善肿瘤检测性能。

要点

  • 从PACS挖掘的临床线标注可转换为边界框用于脑MRI肿瘤检测模型的监督训练。
  • 自标注扩充训练集后,Mask R-CNN模型F1分数达0.954,RetinaNet模型F1分数达0.935。
  • 半监督学习利用未标注数据显著提升检测性能(P < .001)。

核心结论

  • 应用半监督学习于挖掘的图像标注显著改善了肿瘤检测性能,达到优秀的F1分数0.954。

研究设计与样本

  • 回顾性研究,从癌症中心PACS挖掘2012年1月至2017年12月的脑部MRI轴位T1增强图像及线标注,转换为边界框(排除短于1 cm或长于7 cm的框),使用RetinaNet和Mask R-CNN架构进行监督训练;测试集为来自100例患者的754张手动标注图像(403个轴内和56个轴外强化肿瘤)。

关键影像表现/征象

  • 肿瘤检测模型在轴位T1增强图像上检测强化肿瘤,输出边界框。
  • 自标注过程检测训练图像上未标注的肿瘤并自动纠正缺失标签。

诊断标准与关键数值

  • RetinaNet模型F1分数:挖掘数据训练后0.886,自标注后0.935(P < .001)。
  • Mask R-CNN模型F1分数:挖掘数据训练后0.908,自标注后0.954(P < .001)。
  • 测试集包含754张手动标注图像,来自100例患者,共403个轴内和56个轴外强化肿瘤。

临床应用与阅片要点

  • 临床生成的图像标注可被数据挖掘、自动整理并用于半监督训练脑MRI肿瘤检测模型。
  • 该开发流程可扩展至其他影像模态,重新利用未使用的数据孤岛。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Background Artificial intelligence (AI) applications for cancer imaging conceptually begin with automated tumor detection, which can provide the foundation for downstream AI tasks. However, supervised training requires many image annotations, and performing dedicated post hoc image labeling is burdensome and costly. Purpose To investigate whether clinically generated image annotations can be data mined from the picture archiving and communication system (PACS), automatically curated, and used for semisupervised training of a brain MRI tumor detection model. Materials and Methods In this retrospective study, the cancer center PACS was mined for brain MRI scans acquired between January 2012 and December 2017 and included all annotated axial T1 postcontrast images. Line annotations were converted to boxes, excluding boxes shorter than 1 cm or longer than 7 cm. The resulting boxes were used for supervised training of object detection models using RetinaNet and Mask region-based convolutional neural network (R-CNN) architectures. The best-performing model trained from the mined data set was used to detect unannotated tumors on training images themselves (self-labeling), automatically correcting many of the missing labels. After self-labeling, new models were trained using this expanded data set. Models were scored for precision, recall, and F1 using a held-out test data set comprising 754 manually labeled images from 100 patients (403 intra-axial and 56 extra-axial enhancing tumors). Model F1 scores were compared using bootstrap resampling. Results The PACS query extracted 31 150 line annotations, yielding 11 880 boxes that met inclusion criteria. This mined data set was used to train models, yielding F1 scores of 0.886 for RetinaNet and 0.908 for Mask R-CNN. Self-labeling added 18 562 training boxes, improving model F1 scores to 0.935 (P < .001) and 0.954 (P < .001), respectively. Conclusion The application of semisupervised learning to mined image annotations significantly improved tumor detection performance, achieving an excellent F1 score of 0.954. This development pipeline can be extended for other imaging modalities, repurposing unused data silos to potentially enable automated tumor detection across radiologic modalities. © RSNA, 2022 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Swinburne, Yadav, Kim, et al. Semisupervised Training of a Brain MRI Tumor Detection Model Using Mined Annotations. Radiology. 2022. PMID: 35040676. doi:10.1148/radiol.210817

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。